GMFAD: Towards generalized visual recognition via multilayer feature alignment and disentanglement

The deep learning based approaches which have been repeatedly proven to bring benefits to visual recognition tasks usually make a strong assumption that the training and test data are drawn from similar feature spaces and distributions. However, such an assumption may not always hold in various prac...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Haoliang, Wang, Shiqi, Wan, Renjie, Kot, Alex Chichung
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/161899
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English